Face recognition systems are widely deployed in safety-critical applications, including law enforcement, yet they exhibit bias across a range of socio-demographic dimensions, such as gender and race. Conventional wisdom dictates that model biases arise from biased training data. As a consequence, previous works on bias mitigation largely focused on pre-processing the training data, adding penalties to prevent bias from effecting the model during training, or post-processing predictions to debias them, yet these approaches have shown limited success on hard problems such as face recognition. In our work, we discover that biases are actually inherent to neural network architectures themselves. Following this reframing, we conduct the first neural architecture search for fairness, jointly with a search for hyperparameters. Our search outputs a suite of models which Pareto-dominate all other high-performance architectures and existing bias mitigation methods in terms of accuracy and fairness, often by large margins, on the two most widely used datasets for face identification, CelebA and VGGFace2. Furthermore, these models generalize to other datasets and sensitive attributes. We release our code, models and raw data files at https://github.com/dooleys/FR-NAS.

翻译：人脸识别系统被广泛应用于执法等安全关键领域，然而它们在性别和种族等多个社会人口维度上表现出偏见。传统观点认为，模型偏见源于有偏见的训练数据。因此，先前的偏见缓解工作主要集中于预处理训练数据、在训练过程中添加惩罚以防止偏见影响模型，或对预测结果进行后处理以去偏，但这些方法在诸如人脸识别等难题上效果有限。在我们的工作中，我们发现偏见实际上源于神经网络架构本身。基于这一重新认识，我们首次开展了面向公平性的神经网络架构搜索，并同时进行超参数搜索。我们的搜索输出了一系列模型，在准确性和公平性方面，这些模型在两个人脸识别最广泛使用的数据集CelebA和VGGFace2上，以较大优势帕累托支配所有其他高性能架构和现有偏见缓解方法。此外，这些模型能够泛化到其他数据集和敏感属性。我们在https://github.com/dooleys/FR-NAS上发布了代码、模型和原始数据文件。